GitHub

GPTQ Quantization Error While Ovis2.5-9B model

File "/home/azureuser/workspace/adkWorkspace/QuantizationOptimus/ms-swift/ms-swift_env/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate ...
ITU

[328] Software-only modification for encoder quantization and investigation of the impact of the maximum absolute quantization error on coding efficiency

Software-only modification for encoder quantization and investigation of the impact of the maximum absolute quantization error on coding efficiency ...
IEEE

Reducing Neural Networks Quantization Error Through the Change of Feature Correlation

Abstract: The quantization technique of neural networks can achieve a compressed representation of models by reducing weights and activations data bitwidth, accelerating the inference process, and ...
marktechpost

Run MATLAB-Style Code Inside Python by Connecting Octave with the oct2py Library

In this tutorial, we explore how we can seamlessly run MATLAB-style code inside Python by connecting Octave with the oct2py library. We set up the environment on Google Colab, exchange data between ...
GitHub

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

07/02/2025 4.0.0-dev main: Gemma3 4B model compat fix. 05/29/2025 4.0.0-dev main: Falcon H1 model support. Fixed Transformers 4.52+ compat with Qwen 2.5 VL models. 05/19/2025 4.0.0-dev main: Qwen 2.5 ...
IEEE

Spurs in Fractional-N Frequency Synthesizers Resulting From Resolution Mismatch Between the Divider Controller and the DTC: Manifestations, Analysis, and Mitigation

Abstract: The digital-to-time converter (DTC) used in fractional-N phase locked loops is designed to cancel the accumulated quantization error (QE) arising from the ...